Large Language Model (LLM) agents are increasingly deployed as populations of interacting entities, in which consensus --agreement on a shared answer-- emerges as a collective, unengineered behaviour. Prior work on LLM consensus shows that agents can cross-verify their answers and converge towards more factual response...
Emanuele Ricco, Elia Onofri, Vincenzo Sammartino et al.· 0 citations
Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary frontier models, costly and ill-suited to high-throughput monitoring. We investigate whether a panel of cheap open-weight judges (4--9B) can be aggregated to stand in for a...
This work presents TENET, a purpose-built auditing tool whose design decisions are grounded in the structural properties of the secrets targeted and empirically validated against a ground-truth dataset, and proposes mitigation measures and best practices for both Telegram platform developers and third-party Mini App cr...
Andrea Ciccotelli, Federico Zappone, R. Di Pietro· 0 citations
By endowing the minimal-detector receiver of polarization QKD with a conclusive, loss-robust disturbance alarm, the solution lowers the hardware entry cost of security-monitored QKD, hence fostering its adoption at the cost-sensitive network edge.
R. Di Pietro· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
